Skills/PyPI/affinity-mcp

affinity-mcp@0.8.0

CAUTION· not started

Publisher claims: "Affinity MCP server" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher affinity-support · publishing for 262 daysInstalls 3,709Last detonated 20 min ago

Coverage

Not started: dependency install failed; the server itself was not observed.
Tested
the dependency install step · every file read, file written and host contacted by what ran
Not tested
server startup · the tool list · tool behavior

What this means for the label: Caution here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the codeAlso affinity.co, claude.ai — not the publisher's domain; check what for before connecting.
What we saw when it ran
no credential files read · no network
What we could not test
server startup · the tool list · tool behavior

Connect it under the guard. Not started: dependency install failed; the server itself was not observed. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- uvx affinity-mcp

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 0.6.0

vet-skills diff affinity-mcp 0.6.0 0.8.0

In the sandbox, this version reached for nothing 0.6.0 did not. Compared from the two recorded runs, not from source.

No longer contacted
evil.com

0.6.0 was not run in the sandbox (install failed); the comparison covers what static analysis recorded only.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; not started: dependency install failed; the server itself was not observed) on 2026-11-22 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Credential pass-through configuration; Access to sensitive file paths; Access to sensitive file paths. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.2sprocessdependency install exit 1 ·
0.2sclaimednot started: dependency install failed (exit 1); the server itself was not observed
0.2sprocessscript backend runs setup only
0.2sprocessno install scripts to re-run

Static findings

HIGH
Credential pass-through configurationsrc/affinity_mcp/token_shape.py:11 · Credential pass-through configuration — agent relays sensitive credentials- OAuth2 access, impersonation, and happy-proxy tokens: RS256 JWTs — aFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
HIGH
Access to sensitive file pathssrc/affinity_mcp/settings.py:227 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesSettings are loaded from the env file specified by ENV_FILE (default: .env).Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Access to sensitive file pathssrc/affinity_mcp/settings.py:25 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesenv_file=os.getenv("ENV_FILE", ".env"),Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
HIGH
Credential pass-through configurationsrc/affinity_mcp/telemetry.py:116 · Credential pass-through configuration — agent relays sensitive credentialsCREDENTIAL_EXPIRED = "credential_expired" # our proxy token aged out mid-requestFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
CRITICAL
HTML comment carrying imperative instructions to the agentsrc/affinity_mcp/skills/warm-intro/SKILL.md:462 · HTML comment carrying imperative instructions to the agentprettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentsrc/affinity_mcp/skills/warm-intro/SKILL.md:511 · HTML comment carrying imperative instructions to the agentprettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
HTML comment carrying imperative instructions to the agentsrc/affinity_mcp/skills/warm-intro/SKILL.md:520 · HTML comment carrying imperative instructions to the agentprettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionsrc/affinity_mcp/skills/data-migration/SKILL.md:738 · File type combined with upload action — agent may exfiltrate local data files`[list_name]_import.csv`. Use `present_files` to hand the file and upload instructions to the userFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
CRITICAL
HTML comment carrying imperative instructions to the agentsrc/affinity_mcp/skills/warm-intro/SKILL.md:540 · HTML comment carrying imperative instructions to the agentprettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Persistence: instructs the agent to auto-load this skill in future sessionssrc/affinity_mcp/skills/warm-intro/SKILL.md:10 · Persistence: instructs the agent to auto-load this skill in future sessionsmap after paths are surfaced. Always use this skill for warm intro questions — do not attempt toFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Credential pass-through configurationsrc/affinity_mcp/token_shape.py:75 · Credential pass-through configuration — agent relays sensitive credentials- ``user_id`` and ``org_id`` — proxy tokens, from ``sub`` andFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST02
CRITICAL
HTML comment carrying imperative instructions to the agentsrc/affinity_mcp/skills/warm-intro/SKILL.md:471 · HTML comment carrying imperative instructions to the agentprettier-ignoreFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈34,257 tok
5 files · 80 in bundle
Tool list per prompt
≈0 tok
0 tools · 0 per tool
Handshake
no reply
launch to tools/list, stdio
Undocumented tools
0
description under 20 chars · avg 0

Tokens estimated at four characters each. The tool list is re-read by the agent on every turn, so it is the number to compare between servers that do the same job: ranked across the index.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim affinity-support: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
  4. Credential pass-through configuration≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  5. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  6. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim affinity-supportPropose a patch to the maintainer